Rockset announced it has expanded its vector search capabilities
with approximate nearest neighbor (ANN) search, achieving billion-scale
similarity search in the cloud. When coupled with the
LlamaIndex and
LangChain
integrations, the new release enables developers to iterate quickly,
and create more relevant AI experiences at scale. This news comes on the
heels of Rockset raising $44 million in funding and being named a data streaming for AI partner to Confluent.
In April of this year, Rockset introduced support for vector search,
which has gained rapid momentum as more applications employ machine
learning and artificial intelligence to power voice assistants,
chatbots, anomaly detection, recommendation and personalization engines,
and more. However, many large language models (LLMs) generate vector
embeddings with thousands of dimensions, making exact nearest neighbor
search computationally expensive and complex. With the new support for
ANN, Rockset customers can create vector embeddings on any machine
learning model and index them for fast similarity search, at massive
scale. New capabilities allow developers to:
- Create relevant AI experiences at scale by storing and indexing
billions of vectors alongside hundreds of terabytes of metadata,
including text, JSON, geo and time-series data. Leverage the power of
the search index with an integrated SQL engine for metadata filtering as
simple as a SQL WHERE clause.
- Build AI applications with real-time updates by inserting, updating,
and deleting vectors and metadata with indexes built on RocksDB. New
data is reflected in searches in milliseconds with no expensive
reindexing.
- Separate indexing and search with compute-compute separation to scale AI applications in production with confidence.
"Enterprises will only continue to leverage AI if they have the
ability to scale AI applications efficiently, which is why Rockset is
designed for billion-scale vector search in the cloud," said Venkat
Venkataramani, co-founder and CEO of Rockset. "Efficiently incorporating
real-time signals and updates into vector search applications is no
easy feat. We've spent years designing Rockset for real-time updates and
are thrilled that companies can now build AI applications at scale."
Customers are already leveraging the power of Rockset as a vector
database to deploy AI/ML applications at scale. "Iteration and speed of
new ML products were the most important to us," said Sai Ravuru, senior
manager of data science and analytics in a recent case study with JetBlue.
"We saw the immense power of real-time analytics and AI to transform
JetBlue's real-time decision augmentation and automation since stitching
together 3-4 database solutions would have slowed down application
development. With Rockset, we found a database that could keep up with
the fast pace of innovation at JetBlue."